Research map / Label-efficient and robust learning / Semi-supervised learning
Are We Overconfident in Models and Results for Semi-Supervised 3D Medical Image Segmentation?
Jun Li, Ziwei Qin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add the uncertainty branch U(v) to dual-axis assessment (ablation) | TCSeg · LA/Pancreas-CT/BraTS2019 mean | Mean DSC (%): 85.68 -> 86.23 | Improved |
| add the confidence branch C(v) to dual-axis assessment (ablation) | TCSeg · LA/Pancreas-CT/BraTS2019 mean | Mean DSC (%): 85.20 -> 86.23 | Improved |
| add probability-space calibration (ablation) | TCSeg · Three datasets mean | Mean DSC (%): 85.13 -> 86.23 | Improved |
| add image-space structural perturbation (ablation) | TCSeg · Three datasets mean | Mean DSC (%): 84.00 -> 86.23 | Improved |
| add feature-space prototype alignment (ablation) | TCSeg · Three datasets mean | Mean DSC (%): 80.09 -> 86.23 | Improved |
| add feature-space prototype alignment (ablation) | TCSeg · Pancreas-CT 10% labeled | DSC (%): 59.28 -> 81.08 | Improved |
| add feature-space prototype alignment (ablation) | TCSeg · Pancreas-CT 20% labeled | DSC (%): 69.23 -> 83.44 | Improved |
| add semi-supervised tri-space calibration to supervised baseline (ablation) | TCSeg · Three datasets mean | Mean DSC (%): 72.69 -> 86.23 | Improved |
| add feature-space prototypes (ablation) | TCSeg · BraTS2019 10% labeled | DSC (%): 85.57 -> 85.27 | Hurt |
| add probability-space calibration (ablation) | TCSeg · BraTS2019 10% labeled | DSC (%): 85.63 -> 85.27 | Hurt |
| widen confidence band or tolerance (0.01 to 0.10) (ablation) | TCSeg · Sensitivity analysis | DSC | No clear effect |
| report last instead of best checkpoint | TCSeg · LA 10% labeled | DSC (%): 90.28 -> 90.73 | No clear effect |
Closest papers by meaning
- Beyond Random Sampling: Distribution-Aware Alignment for Semi-Supervised Medical Image Segmentation (ECCV 2026 · similarity 0.89)
- Steady Progress Beats Stagnation: Mutual Aid of Foundation and Conventional Models in Mixed Domain Semi-Supervised Medical Image Segmentation (CVPR 2025 · similarity 0.87)
- DyCON: Dynamic Uncertainty-aware Consistency and Contrastive Learning for Semi-supervised Medical Image Segmentation (CVPR 2025 · similarity 0.87)
- Towards Fairness under Label Bias in Image Segmentation: Impact, Measurement and Mitigation (NeurIPS 2026 · similarity 0.87)
- Annotation Ambiguity Aware Semi-Supervised Medical Image Segmentation (CVPR 2025 · similarity 0.86)
- SGTC: Semantic-Guided Triplet Co-training for Sparsely Annotated Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
